metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
b bag, a woman with long dark curly hair, wearing a white t-shirt and tan
pants, is holding a beige tote bag with a black design of two fish on it
and the word "pisces" written in black on the bag. She is standing in
front of a glass window, her left hand resting on her hip. The background
is blurred, with lights visible through the window.
output:
url: images/1.png
- text: >-
b bag, A close-up view of a white canvas tote bag with a yellow skateboard
and a white dove drawn on it. Above the dove, the words "FUCK OFF MATE"
are written in black letters. The person is wearing a yellow shirt and
blue jeans. The background of the bag is a white wall made up of white
tiles.
output:
url: images/2.png
- text: >-
b bag, A close-up view of a beige tote bag with a green square on the
front that reads "not ur babe". The square has a white face with black
hair and white sunglasses on it. The bag is held up by two beige handles.
To the left of the bag is a pair of blue denim jeans.
output:
url: images/3.png
- text: >-
b bag, a woman is holding a white tote bag with a black drawing of a
flying saucer and the words "See ya later" written in black ink on the
bag. The woman is wearing an orange shirt and blue jeans, and her hair is
dark brown. The backdrop of the bag is a stark white tiled wall.
output:
url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Bg bag
license: creativeml-openrail-m
Model description for Bg-Bag
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 16 & 2230 |
Epoch | 14 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 25
Best Dimensions & Inference
Dimensions | Aspect Ratio | Recommendation |
---|---|---|
1280 x 832 | 3:2 | Best |
1024 x 1024 | 1:1 | Default |
Inference Range
- Recommended Inference Steps: 30–35
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Bg-Bag"
trigger_word = "Ctoon++"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Bg bag
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.